Step-Down Analysis for Changes in the Covariance Matrix and Other Parameters

Step-down diagnostic analysis to infer which means have changed (after detection of a shift in the mean vector) is familiar in multivariate statistical process control. We show how to include in the diagnostic analysis the elements of the covariance matrix and other higher order moments and give practical examples. We use the asymptotic normality of maximum-likelihood estimators to classify the parameters that describe the prior- and post-shift distributions into those for which there is significant evidence of a shift and those for which such evidence is lacking. This diagnostic information can be useful in guiding the search for the cause(s) of the shift. For practical applications, the choice of parameterization may affect the ease of interpretation of the diagnostic results. It may be more informative to use standard deviations and correlation coefficients instead of variances and covariances, and this approach is illustrated in our analysis and examples. We also consider application to distributions other than the multivariate normal and give an example with a multivariate gamma distribution. Although illustrated with independent and identically distributed observations, the proposed methodology is more general.

[1]  D. Andrews.  Tests for Parameter Instability and Structural Change with Unknown Change Point , 1993 .

[2]  N. L. Johnson,et al.  Multivariate Analysis , 1958, Nature.

[3]  Joseph J. Pignatiello,et al.  Diagnosing Signals from T2 and Chi-Squared Multivariate Control Charts , 1998 .

[4]  Youn Min Chou,et al.  Applying Hotelling's T2 Statistic to Batch Processes , 2001 .

[5]  Douglas C. Montgomery,et al.  A Discussion on Statistically-Based Process Monitoring and Control , 1997 .

[6]  Fallaw Sowell,et al.  Optimal tests for parameter instability in the generalized method of moments framework , 1996 .

[7]  William H. Woodall,et al.  Ch. 13. Control chart schemes for monitoring the mean and variance of processes subject to sustained shifts and drifts , 2003 .

[8]  Nola D. Tracy,et al.  Decomposition of T2 for Multivariate Control Chart Interpretation , 1995 .

[9]  Roger M. Sauter,et al.  Introduction to Statistical Quality Control (2nd ed.) , 1992 .

[10]  Bronwyn H Hall,et al.  Estimation and Inference in Nonlinear Structural Models , 1974 .

[11]  William H. Woodall,et al.  A Comparison of Multivariate Control Charts for Individual Observations , 1996 .

[12]  N. L. Johnson,et al.  Linear Statistical Inference and Its Applications , 1966 .

[13]  Joe H. Sullivan,et al.  A Self-Starting Control Chart for Multivariate Individual Observations , 2002, Technometrics.

[14]  William N. Goetzmann,et al.  Long-Term Global Market Correlations , 2001 .

[15]  Statistical Methods for Quality Improvement, 2nd Ed. , 2000 .

[16]  Marion R. Reynolds,et al.  Individuals control schemes for monitoring the mean and variance of processes subject to drifts , 2001 .

[17]  A. Erhan Mergen,et al.  Identifying the Sources for Out-of-COntrol Signals When the T2 Control Chart Is Used , 1995 .

[18]  Joseph J. Pignatiello,et al.  DIAGNOSING SIGNALS FROM T 2 AND χ2 MULTIVARIATE CONTROL CHARTS , 1998 .

[19]  Marion R. Reynolds,et al.  Control Charts and the Efficient Allocation of Sampling Resources , 2004, Technometrics.

[20]  Alexander Shapiro,et al.  The asymptotic covariance matrix of sample correlation coefficients under general conditions , 1986 .

[21]  William H. Woodall,et al.  Change-point detection of mean vector or covariance matrix shifts using multivariate individual observations , 2000 .

[22]  John C. Young,et al.  A Practical Approach for Interpreting Multivariate T2 Control Chart Signals , 1997 .

[23]  W. Greene,et al.  计量经济分析 = Econometric analysis , 2009 .

[24]  Joseph J. Pignatiello,et al.  IDENTIFYING THE TIME OF A STEP-CHANGE WITH X 2 CONTROL CHARTS , 1998 .

[25]  York Marcel Dekker.  The State of Statistical Process Control as We Proceed into the 21st Century , 2000 .

[26]  A. M. Wesselman,et al.  THE ASYMPTOTIC VARIANCE MATRIX OF THE SAMPLE CORRELATION MATRIX , 1990 .

[27]  Maman A. Djauhari,et al.  Improved Monitoring of Multivariate Process Variability , 2005 .

[28]  S. Bersimis,et al.  IDENTIFYING THE OUT OF CONTROL VARIABLE IN A MULTIVARIATE CONTROL CHART , 2002 .

[29]  William H. Woodall,et al.  A Control Chart for Preliminary Analysis of Individual Observations , 1996 .